Artificial Intelligence Engineer
We are seeking an experienced AI Professional to build and optimize Retrieval-Augmented Generation models for search across large-scale medical and scientific documents.
About the Role:
* Bulk up our team by contributing your expertise in building scalable search systems.
* Collaborate with us on hands-on experimentation, model development, and backend engineering with deployments to non-prod environments.
* Fine-tune Large Language Models (LLMs) for textual Retrieval-Augmented Generation use cases.
Key Responsibilities:
1. Pull together a knowledge graph of pre-processed data from over half a billion documents.
2. Embed those documents into searchable contexts using our custom RAG architecture.
3. Design strategies to improve automated evaluation pipelines.
4. Implement semantic chunking for accurate search results.
Requirements:
* You must have at least 1 year's experience as a Search or AI Engineer.
* Familiarity with OpenSearch technologies is a plus.
* You need 2+ years of Python development experience including API creation, model training, testing, and general backend programming.
* Languages you've worked with should include tools like LangChain.
* You should be able to communicate clearly and provide updates independently.
Nice to Have Skills:
* AWS infrastructure familiarity such as IAM, VPC, S3.
* Previous work with RAG architectures particularly textual use cases.